Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine

This study aimed to accurately map burned forest areas and analyze the spatial distribution of forest fires under complex terrain conditions. This study integrates Landsat 8, Sentinel-2, and MODIS data to map burned forest areas in the complex terrain of western Yunnan. A machine learning workflow w...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Chen, Weili Kou, Wenna Miao, Xiong Yin, Jiayue Gao, Weiyu Zhuang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/5/741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030874885619712
author Yue Chen
Weili Kou
Wenna Miao
Xiong Yin
Jiayue Gao
Weiyu Zhuang
author_facet Yue Chen
Weili Kou
Wenna Miao
Xiong Yin
Jiayue Gao
Weiyu Zhuang
author_sort Yue Chen
collection DOAJ
description This study aimed to accurately map burned forest areas and analyze the spatial distribution of forest fires under complex terrain conditions. This study integrates Landsat 8, Sentinel-2, and MODIS data to map burned forest areas in the complex terrain of western Yunnan. A machine learning workflow was developed on Google Earth Engine by combining Dynamic World land cover data with official fire records, utilizing a logistic regression-based feature selection strategy and an enhanced SNIC segmentation GEOBIA framework. The performance of four classifiers (RF, SVM, KNN, CART) in burn detection was evaluated through a comparative analysis of their spectral–spatial discrimination capabilities. The results indicated that the RF classifier achieved the highest performance, with an overall accuracy of 96.32% and a Kappa coefficient of 0.951. Spatial analysis further revealed that regions at medium altitudes (800–1600 m) and moderate slopes (15–25°) are more prone to forest fires. This study demonstrates a robust approach for generating accurate large-scale forest fire maps and provides valuable insights for effective fire management in complex terrain areas.
format Article
id doaj-art-0e69e896c3aa4c04ba44bbd9a8c79012
institution DOAJ
issn 2072-4292
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-0e69e896c3aa4c04ba44bbd9a8c790122025-08-20T02:59:07ZengMDPI AGRemote Sensing2072-42922025-02-0117574110.3390/rs17050741Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth EngineYue Chen0Weili Kou1Wenna Miao2Xiong Yin3Jiayue Gao4Weiyu Zhuang5College of Forestry, Southwest Forestry University, Kunming 650224, ChinaCollege of Big Data and Intelligence Engineering, Southwest Forestry University, Kunming 650224, ChinaCollege of Forestry, Southwest Forestry University, Kunming 650224, ChinaCollege of Forestry, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Forestry, Southwest Forestry University, Kunming 650224, ChinaCollege of Forestry, Southwest Forestry University, Kunming 650224, ChinaThis study aimed to accurately map burned forest areas and analyze the spatial distribution of forest fires under complex terrain conditions. This study integrates Landsat 8, Sentinel-2, and MODIS data to map burned forest areas in the complex terrain of western Yunnan. A machine learning workflow was developed on Google Earth Engine by combining Dynamic World land cover data with official fire records, utilizing a logistic regression-based feature selection strategy and an enhanced SNIC segmentation GEOBIA framework. The performance of four classifiers (RF, SVM, KNN, CART) in burn detection was evaluated through a comparative analysis of their spectral–spatial discrimination capabilities. The results indicated that the RF classifier achieved the highest performance, with an overall accuracy of 96.32% and a Kappa coefficient of 0.951. Spatial analysis further revealed that regions at medium altitudes (800–1600 m) and moderate slopes (15–25°) are more prone to forest fires. This study demonstrates a robust approach for generating accurate large-scale forest fire maps and provides valuable insights for effective fire management in complex terrain areas.https://www.mdpi.com/2072-4292/17/5/741burned forest areasgeographic object-based image analysis (GEOBIA)Sentinel-2Landsat 8MODIS
spellingShingle Yue Chen
Weili Kou
Wenna Miao
Xiong Yin
Jiayue Gao
Weiyu Zhuang
Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
Remote Sensing
burned forest areas
geographic object-based image analysis (GEOBIA)
Sentinel-2
Landsat 8
MODIS
title Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
title_full Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
title_fullStr Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
title_full_unstemmed Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
title_short Mapping Burned Forest Areas in Western Yunnan, China, Using Multi-Source Optical Imagery Integrated with Simple Non-Iterative Clustering Segmentation and Random Forest Algorithms in Google Earth Engine
title_sort mapping burned forest areas in western yunnan china using multi source optical imagery integrated with simple non iterative clustering segmentation and random forest algorithms in google earth engine
topic burned forest areas
geographic object-based image analysis (GEOBIA)
Sentinel-2
Landsat 8
MODIS
url https://www.mdpi.com/2072-4292/17/5/741
work_keys_str_mv AT yuechen mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine
AT weilikou mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine
AT wennamiao mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine
AT xiongyin mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine
AT jiayuegao mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine
AT weiyuzhuang mappingburnedforestareasinwesternyunnanchinausingmultisourceopticalimageryintegratedwithsimplenoniterativeclusteringsegmentationandrandomforestalgorithmsingoogleearthengine